MM-AlignBench

What is MM-AlignBench?

A benchmark for evaluating MLLMs' alignment with human preferences. It includes 252 high-quality, human-annotated samples with diverse image types and…

Released

2025-02-25

Modality

multimodal

Evaluates

多模态, Multimodal, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MM-AlignBench

MM-AlignBench paper and code

• Paper https://arxiv.org/abs/2502.18411
• Code https://github.com/PhoenixZ810/OmniAlign-V

Which sources cite MM-AlignBench?

• MM-AlignBench

Related 多模态, Multimodal, 多模态模型, VLM, 跨模态推理, Cross-modal Reasoning, 不支持, Unsupported benchmarks

• 3DCodeBench
• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AECBench